Steve PRO

wangzhang

·

AI & ML interests

LLM Abliteration & Weight-Space Attacks, Refusal Direction Analysis, LoRA Reverse Engineering, TPE Hyperparameter Optimization, Mixture-of-Experts Abliteration, SSM/Hybrid Architecture Research, Activation Engineering, Vision-Language Models, Representation Engineering

Recent Activity

liked a model 10 days ago

wangzhang/gemma-4-12B-it-abliterix

updated a collection 10 days ago

Gemma-Abliterated

updated a model 10 days ago

wangzhang/gemma-4-12B-it-abliterix

View all activity

Organizations

None yet

liked a model 10 days ago

wangzhang/gemma-4-12B-it-abliterix

Text Generation • 12B • Updated 10 days ago • 63 • 3

liked 3 models about 1 month ago

wangzhang/granite-4.1-8b-abliterated

Text Generation • 8B • Updated May 28 • 6 • 2

wangzhang/granite-4.1-30b-abliterated

Text Generation • 29B • Updated May 29 • 4 • 1

wangzhang/granite-4.1-3b-abliterated

Text Generation • 3B • Updated May 28 • 4 • 1

liked 8 models 2 months ago

wangzhang/Qwen3.6-27B-abliterated

Image-Text-to-Text • 27B • Updated May 2 • 2k • 13

wangzhang/Qwen3.6-27B-abliterated-GGUF

Text Generation • 27B • Updated May 2 • 3.73k • 7

wangzhang/Qwen3.6-27B-abliterated-v1

Image-Text-to-Text • 27B • Updated Apr 23 • 12 • 5

wangzhang/Qwen3.6-35B-A3B-abliterated-v2

35B • Updated Apr 20 • 571 • 9

wangzhang/gemma-4-31B-it-abliterated-GGUF

Text Generation • 31B • Updated Apr 29 • 1.49k • 8

wangzhang/gemma-4-26B-A4B-it-abliterix-GGUF

25B • Updated Apr 20 • 957 • 8

wangzhang/gpt-oss-120b-abliterated

Text Generation • 117B • Updated Apr 21 • 86 • 5

wangzhang/gpt-oss-20b-abliterated-GGUF

Text Generation • 21B • Updated Apr 20 • 429 • 4

liked 8 models 3 months ago

wangzhang/Qwen3.6-35B-A3B-abliterated-GGUF

35B • Updated Apr 17 • 1.35k • 3

wangzhang/Qwen3.6-35B-A3B-abliterated

35B • Updated Apr 17 • 227 • 17

wangzhang/gemma-4-26B-A4B-it-abliterix

26B • Updated Apr 20 • 2.61k • 26

wangzhang/Llama-3-8B-Instruct-RR-Abliterated

Text Generation • 8B • Updated Apr 13 • 27 • • 2

wangzhang/Mistral-7B-Instruct-RR-Abliterated

Text Generation • 7B • Updated Apr 14 • 9 • 1

wangzhang/Llama-3-8B-Instruct-DeepRefusal-Broken

Text Generation • 8B • Updated Apr 13 • 19 • 4

wangzhang/gemma-4-E4B-it-abliterix

8B • Updated Apr 11 • 273 • 11

wangzhang/gpt-oss-20b-abliterated

Text Generation • 21B • Updated Apr 20 • 17k • 4